paddlets.models.forecasting.dl.paddle_base

class PaddleBaseModel(in_chunk_len: int, out_chunk_len: int, skip_chunk_len: int = 0)[source]

Bases: BaseModel

Base class for all paddle deep learning models.

Parameters

in_chunk_len (int) – The size of the loopback window, i.e., the number of time steps feed to the model.
out_chunk_len (int) – The size of the forecasting horizon, i.e., the number of time steps output by the model.
skip_chunk_len (int) – Optional, the number of time steps between in_chunk and out_chunk for a single sample. The skip chunk is neither used as a feature (i.e. X) nor a label (i.e. Y) for a single sample. By default, it will NOT skip any time steps.

_network

A paddle.nn.Layer instance.

Type: paddle.nn.Layer

_optimizer

Type: paddle.optimizer.Optimizer

_callback_container

a container containing one or more callback instance(s).

Type: paddlets.models.dl.paddlepaddle.callbacks.CallbackContainer

abstract fit(train_data: Union[TSDataset, List[TSDataset]], valid_data: Optional[Union[TSDataset, List[TSDataset]]] = None)[source]

Fit a paddle deep learning model instance.

Any non-abstract classes inherited from this class should implement this method.

Parameters

train_data (Union[TSDataset, List[TSDataset]]) – training dataset.
valid_data (Optional[Union[TSDataset, List[TSDataset]]]) – validation dataset, optional.

abstract predict(data: TSDataset) → TSDataset[source]

Make prediction.

Any non-abstract classes inherited from this class should implement this method.

Parameters: data (TSDataset) – TSDataset to predict.
Returns: Predicted result, in type of TSDataset.
Return type: TSDataset

save(path: str, network_model: bool = False, dygraph_to_static=True, batch_size: Union[None, int] = None) → None[source]

Saves a PaddleBaseModel instance to a disk file.

1> A PaddleBaseModel (or any child classes inherited from PaddleBaseModel) instance have a set of member variables, they can be divided into 3 categories: pickle-serializable members (e.g. python built-in type such as int, str, dict, etc.), paddle-related pickle-not-serializable members (e.g. paddle.nn.Layer, paddle.optimizer.Optimizer), paddle-not-related pickle-not-serializable members.

2> To call this method, self._network and self._optimizer must not be None.

Parameters

path (str) – A path string containing a model file name.
network_model (bool) – Save network model structure and parameters separately for Paddle Inference or not, default False.
dygraph_to_static (bool) – Change network from dygraph to static or not, it works when network_model==True, default True.
batch_size (int) – The fixed batch size for the param input_spec of network_model save, it works when network_model==True, default None.

Raises

ValueError –

static load(path: str) → PaddleBaseModel[source]

Loads a PaddleBaseModel from a file.

As optimizer does not affect the model prediction results, currently optimizer will NOT be loaded.

Parameters: path (str) – A path string containing a model file name.
Returns: the loaded PaddleBaseModel instance.
Return type: PaddleBaseModel